Re: Sampling [message #29093 is a reply to message #29082] |
Tue, 23 April 2024 07:55 |
Bridgette-DHS
Messages: 3199 Registered: February 2013
|
Senior Member |
|
|
Following is a response from Senior DHS staff member, Tom Pullum:
The level of the Mean Relative Error varies from one indicator to another. DHS surveys are generally designed to have acceptable levels of MRE for strata, which are usually combinations of urban/rural residence crossed with the first admin level, or regions. Just a few surveys are designed for acceptable estimates at level 2, or districts. We recommend that you calculate confidence intervals for estimates, including adjustments for the survey design, and make your own judgement about acceptability, rather than using some arbitrary cutoff such as 20%.
|
|
|